Abstract:
This dataset contains four types of data: i) IceNet's 93-day pan-Arctic sea ice concentration forecasts, initialised each day between 26th July - 12th December for the years 2020-2022 inclusive (140 forecasts per year), ii) neural network weights for the IceNet model used to generate the forecasts, iii) a Shapefile for the coastline of Victoria Island (Nunavut, Canada), which was used to estimate caribou sea ice crossing-start times, and iv) CSV files with results linking sea ice concentration values to caribou sea ice crossing-start times. This data was used to explore if and how sea ice forecasts from the IceNet model could give early-warning of Dolphin and Union caribou migration times from Victoria Island to the mainland, by predicting key sea ice concentration thresholds.
This work was supported under the WWF-UK Arctic IceNet grant (project number GB085600), the EPSRC Grant EP/Y028880/1 and the Environment and Sustainability Grand Challenge at the Alan Turing Institute.
Keywords:
Coranation Gulf, Northwest Passage, caribou, forecast, migration, sea ice
Bowler, E., Byrne, J., Leclerc, L., Roberto-Charron, A., Rogers, M., Cavanagh, R., Harasimo, J., Lancaster, M., Chan, R., Strickson, O., Wilkinson, J., Downie, R., Hosking, J., & Andersson, T. (2025). Pan-Arctic 93-day sea ice concentration forecasts from the IceNet model and mappings between sea ice concentration and Dolphin and Union caribou sea ice crossing-start times (Version 1.0) [Data set]. NERC EDS UK Polar Data Centre. https://doi.org/10.5285/8738b3cb-52c7-4b36-aa6d-6e15c0b46ba4
| Access Constraints: | No restrictions apply. |
|---|---|
| Use Constraints: | Data supplied under Open Government Licence v3.0 http://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/. |
| Creation Date: | 2025-04-07 |
|---|---|
| Dataset Progress: | Complete |
| Dataset Language: | English |
| ISO Topic Categories: |
|
| Parameters: |
|
| Personnel: | |
| Name | UK Polar Data Centre |
| Role(s) | Metadata Author |
| Organisation | British Antarctic Survey |
| Name | Ellen Bowler |
| Role(s) | Investigator, Technical Contact |
| Organisation | British Antarctic Survey |
| Name | James Byrne |
| Role(s) | Investigator |
| Organisation | British Antarctic Survey |
| Name | Lisa-Marie Leclerc |
| Role(s) | Investigator |
| Organisation | Government of Nunavut |
| Name | Amelie Roberto-Charron |
| Role(s) | Investigator |
| Organisation | Government of Nunavut |
| Name | Martin S J Rogers |
| Role(s) | Investigator |
| Organisation | British Antarctic Survey |
| Name | Rachel D Cavanagh |
| Role(s) | Investigator |
| Organisation | British Antarctic Survey |
| Name | Jason Harasimo |
| Role(s) | Investigator |
| Organisation | WWF |
| Name | Melanie L Lancaster |
| Role(s) | Investigator |
| Organisation | WWF |
| Name | Ryan S Y Chan |
| Role(s) | Investigator |
| Organisation | The Alan Turing Institute |
| Name | Oliver Strickson |
| Role(s) | Investigator |
| Organisation | The Alan Turing Institute |
| Name | Jeremy Wilkinson |
| Role(s) | Investigator |
| Organisation | British Antarctic Survey |
| Name | Rod Downie |
| Role(s) | Investigator |
| Organisation | WWF |
| Name | J S Hosking |
| Role(s) | Investigator |
| Organisation | British Antarctic Survey |
| Name | Tom R Andersson |
| Role(s) | Investigator |
| Organisation | British Antarctic Survey |
| Parent Dataset: | N/A |
| Reference: | Ellen Bowler, James Byrne, Lisa-Marie Leclerc, Amélie Roberto-Charron, Martin S.J. Rogers, Rachel D. Cavanagh, Jason Harasimo, Melanie L. Lancaster, Ryan S.Y. Chan, Oliver Strickson, Jeremy Wilkinson, Rod Downie, J. Scott Hosking, Tom R. Andersson (2025). AI sea ice forecasts for Arctic conservation: A case study predicting the timing of caribou sea ice migrations. Ecological Solutions and Evidence. (submitted) | |
|---|---|---|
| Quality: | IceNet makes predictions based on ERA5 reanalysis data and OSI-SAF SIC data - for information on their errors see their associated documentation. IceNet's SIC values were set to zero over a land mask. | |
| Lineage/Methodology: | The IceNet model used in this dataset is an ensemble of 10 individual U-Net deep learning models, whose forecasts are averaged to compute the ensemble mean. IceNet's daily inputs comprise sea ice concentration (SIC), 11 climate variables, statistical SIC forecasts, and metadata. IceNet is trained to forecast the next 93 days of daily SIC maps at 25 km resolution. IceNet's training data comprises climate simulations covering 1850-2100 and observational (reanalysis and satellite) data from 1979-2015. Observational data from 2015-2019 was used to validate the model during training, and 2020-2022 was used as the test set. The IceNet forecasts for the 2020-2022 test date ranges are provided in netCDF format. The final model weights used to generate the test forecasts are provided as Tensorflow neural network files (HDF5). We use held-out data from 2015-2022 to compare IceNet's forecasting skill to a dynamical model (ECMWF SEAS5). These results are provided in a summary CSV file. Satellite telemetry records from collared caribou were analysed alongside SIC satellite data products to generate caribou/SIC relationships. Satellite telemetry data is held by the Government of Nunavut and is not openly available. Here we present an overview of the analysis and primary results generated, removing specifics relating to the telemetry dataset where required. Caribou sea ice crossing-start points were defined by creating an outline of Victoria Island and assessing when and where each caribou left the island and began travelling over sea ice. This Victoria Island coastline is given as a Shapefile, and was derived from OpenStreetMap data. SIC values at crossing-start points were extracted from the Ocean and Sea Ice Satellite Application Facility (OSI-SAF) and the Advanced Microwave Scanning Radiometer 2 (AMSR2) passive microwave satellite records, provided as CSV files. These OSI-SAF and AMSR2 SIC records were used to produce a mapping between a SIC threshold and the percent of collared caribou which had migrated before that SIC threshold. These sic/percent-migrated mappings are provided as CSV files, and can be used to convert IceNet forecasts to expected caribou sea ice crossing-start dates. The full process for generating these sets of results are described in detail in the Methods section and supplementary material of the associated paper. The GitHub repository also contains code associated with the analysis. |
|
| Temporal Coverage: | |
|---|---|
| Start Date | 2020-07-01 |
| End Date | 2020-12-12 |
| Start Date | 2021-07-01 |
| End Date | 2021-12-12 |
| Start Date | 2022-07-01 |
| End Date | 2022-12-12 |
| Spatial Coverage: | |
| Latitude | |
| Southernmost | 66.5 |
| Northernmost | 69.5 |
| Longitude | |
| Westernmost | -117 |
| Easternmost | -103 |
| Altitude | |
| Min Altitude | N/A |
| Max Altitude | N/A |
| Depth | |
| Min Depth | N/A |
| Max Depth | N/A |
| Data Resolution: | |
| Latitude Resolution | N/A |
| Longitude Resolution | N/A |
| Horizontal Resolution Range | 10 km - < 50 km or approximately .09 degree - < .5 degree |
| Vertical Resolution | N/A |
| Vertical Resolution Range | N/A |
| Temporal Resolution | N/A |
| Temporal Resolution Range | N/A |
| Location: | |
| Location | Arctic |
| Detailed Location | Victoria Island, Nunavut, Canada |
| Data Collection: | IceNet forecasts were generated using the Python library icenet v0.2.6 and can be recreated with icenet-pipeline and icenet@v0.2.x. Results in the analysis were generated in Python v3.9 using the libraries listed in https://github.com/EllieBowler/icenet-caribou-paper. |
|---|
| Distribution: | |
|---|---|
| Distribution Media | Online Internet (HTTP) |
| Distribution Size | 56 GB |
| Distribution Format | N/A |
| Fees | N/A |
| Data Storage: | The dataset consists of the 2020-2022 IceNet forecasts, 1 netCDF file per year, 10 TensorFlow neural network HDF5 files, 1 Victoria Island buffer Shapefile, and the paper results as 6 CSV files. |